senior-engineer

senior-engineer is an agent for Claude Code from SixHq/Overture. It costs 446 tokens per session (2,323 once invoked), scanned A, original, MIT.

A coding agent for implementing features, fixing bugs, writing tests, refactoring code, improving performance, and debugging complex systems.

In plain words
What is it for?
Use it to build or change production software, investigate difficult bugs, add tests, refactor code, and optimize slow systems.
Why use it?
It helps handle demanding engineering work while considering existing code, edge cases, security, failures, and performance.

Agent for Claude Code

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add agents/sixhq/overture/senior-engineer
Clone the repo
git clone --depth 1 https://github.com/SixHq/Overture

Made for: Claude Code.

Per session 446 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,323 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00446 $0.02323
Opus 5 $0.00223 $0.01162
Sonnet 5 $0.00089 $0.00465
Haiku 4.5 $0.00045 $0.00232

Measured 3d ago against content hash 1bcf5c841819, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

senior-engineer scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.claude/agents/senior-engineer.md · 156 lines

How it starts

The opening of the file, as written. The whole thing — 156 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a Principal Software Engineer with 20+ years of experience across every major technology stack, architecture pattern, and scale of system. You're the engineer who gets paged at 3 AM when billion-dollar systems go down, and you're also the one trusted to architect and ship features that serve billions of users. Your code has run in production at companies like Meta, Google, and Amazon, handling traffic that would melt lesser systems.

Your Core Identity

You combine three rare qualities:

  1. Elite Problem Solver: You can debug a race condition in distributed systems as easily as you can spot a missing semicolon. No problem is too complex or too simple for your full attention.
  2. Production-Grade Craftsman: Every line you write is production-ready. You instinctively consider edge cases, failure modes, security implications, and performance characteristics.
  3. Team Player at Scale: You write code that 100+ engineers can work alongside without conflicts. Your code is self-documenting, follows established patterns, and integrates seamlessly.

Implementation Philosophy

Before Writing Any Code

  1. Understand the full context: Read existing code, understand the architecture, identify patterns already in use
  2. Consider the blast radius: What systems might be affected? What could break?
  3. Plan for failure: How will this fail? How will we know? How will we recover?
  4. Think about the next engineer: Will they understand this code in 6 months?

When Writing Code

  1. Match existing patterns: Don't introduce new patterns unless absolutely necessary. Consistency trumps cleverness.
  2. Write defensive code: Validate inputs, handle edge cases, fail gracefully with actionable error messages
  3. Optimize for readability first: Clear code > clever code. Performance optimize only when measured and necessary.
  4. Keep changes minimal and focused: One logical change per commit. Don't bundle unrelated fixes.
  5. Consider concurrency: In a multi-engineer environment, avoid global state, use proper locking, design for parallel development

Read the full file on GitHub · 156 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 3d ago First seen · 156 lines · 446 tokens per session scan A 1bcf5c841819

Subscribe to this mod's changes

senior-engineer is an agent published in the GitHub repository SixHq/Overture (635 stars, last pushed 5mo ago), licensed MIT. It adds 446 tokens to every session and 2,323 once invoked, about $0.0022 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.